JPH08129476A - Voice data input device - Google Patents

Abstract

PURPOSE: To perform data input by only voice by a person who performs the data input without watching a screen by performing a voice output of data classified by items and commands for which voice confirmations are performed by a voice synthesis, inputting the item data inputted by voice input in the item, displaying the data and processing the data in accordance with the command inputted by voice. CONSTITUTION: An uttered voice is inputted with a microphone 2, a voice recognition is performed for the voice in a voice recognition synthesizing device 3, and the recognized word resulted is delivered to an operating system by a code system. With this delivery, a voice synthesis is performed for the recognized word, the data classified by items and a command and the synthesized one is delivered to a worker by voice from a headphone 1. If the delivered word is the coment data classified by items, the data is inputted in the system and the data is displayed on the item of the screen on a display device 7. If the delivered word is the command, a processing is performed in accordance with the command. As a result, when a data input is performed, the data input can be performed by only voice without watching the screen.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice data input device. In particular, the present invention relates to a voice data input device which is effective when inputting data only by voice.

[0002]

2. Description of the Related Art In conventional data processing, data input is a conversation such as displaying items that need to be input on the screen of a display device and inputting data from the keyboard for each of the displayed items. It was often done in a format.
In this case, the person who inputs the data cannot release the hand from the keyboard or the eyes from the screen during the data input. For this reason, when performing data input while performing work, it is necessary to temporarily interrupt work and enter data, or prepare a person to enter data separately and have that person enter the data. was there.

Since voice recognition technology has been developed,
It is conceivable to input data by voice. However, in data input, it is often premised that the user inputs items while confirming the items to be input on the screen, and it has been difficult to completely replace with voice input.

[0004]

SUMMARY OF THE INVENTION It is an object of the present invention to provide a voice data input device which allows a person who inputs data to input data only by voice without looking at the screen when inputting data. .

[0005]

To achieve the above object, the present invention provides a voice data input device for inputting voice by itemized data, a voice input device for inputting voice, a voice output device for outputting voice, and an input. Means for displaying the itemized data that has been input, a means for recognizing the voice-inputted itemized data and commands by voice, a means for outputting the voiced itemized data and commands by voice synthesis, and a voice input A voice data input device comprising: means for inputting / displaying item data in the item; and means for performing processing in accordance with a voice input command.

[0006]

In the present invention, all data input can be input by voice, and the confirmation of the input is also answered by voice. Therefore, when inputting data, other work can be performed without interruption.

[0007]

Embodiments of the present invention will be described below with reference to the drawings.

The present invention will be described by applying it to a pathological examination support system. However, the present invention is not limited to the pathological examination support system and can be used when data is input.

In the pathological examination, a pathological examination support system using a computer has been desired in order to prepare a report, construct a database, analyze data, and the like. However, the problem was how to input the data. It is necessary to perform the work of pathological examination while looking at the microscope. Therefore, if it is possible to easily input the data of the findings obtained while observing the microscope, the data is input at the same time as the data is generated, so that it is easy to create the report and the database.

However, it was not possible with conventional systems to input data without taking an eye off the microscope while working on the microscope. According to the present invention, since all data can be inputted by voice while looking at the microscope, the work efficiency can be improved.

FIG. 1 shows the system configuration of this system. In FIG. 1, reference numeral 1 is a headphone (earphone or the like), and 2 is a microphone with which a voice can be input and a voice response from the system can be heard. Three
Is a speech recognition synthesizer used for data input of the present invention,
It is connected to the headphone 1 and the microphone 2 to recognize a voice and input it as a code, or perform voice synthesis for a voice response. 4 is a CPU, 5 is a memory, 6 is a display device interface, 7 is a display device, 8 is a keyboard / mouse interface, 9 is a keyboard, 10
Is a mouse, and 11 is an external storage device such as a disk device, which constitutes a computer system. In addition,
A printer and the like (not shown) are also connected to this computer system.

Regarding the data input to the pathological examination support system by voice in the above computer system, FIG.
Will be explained.

First, the operator utters a pathological finding or command while looking at the microscope (S21). The uttered voice is input by the microphone 2 and recognized by the voice recognition / synthesis device 3 (S23), and the resulting recognition word (pathological finding data or command) is in the form of an OS (operating system). ) (S
25). Along with this, the recognized words are
The voice is synthesized and transmitted to the operator by voice from the headphones 1 (S26). The recognized words (pathological finding data and commands) are transmitted from the OS to the pathological examination support system, which is an application program (S27). In the pathological examination support system, if the sent word is pathological finding data, the data is input to the system and displayed in the item on the screen of the display device 7 (S28). If the sent word is a command, processing according to the command is performed (S29).

It should be noted that normal data input (pathological finding data and commands) can be naturally performed on the pathological examination support system using a keyboard, a mouse or the like (S3).
0).

Now, the operation of the speech recognition / synthesis device 3 will be described in detail with reference to the flowchart shown in FIG. When a voice is input from the microphone 2, the voice waveform is digitized by A / D conversion (S31). The digitized voice waveform is compared with the voice pattern stored in the voice recognition / synthesis device 3 (S32). For this comparison, HMM (Hidden
Markov Model) method is used. When the matched voice pattern exists (S33), the word corresponding to the matched voice pattern is output (S34). The output word is subjected to a simple grammatical check regarding attributes such as input order and numbers (S35), and the word that has passed the check is set as a recognition word. Then, the voice corresponding to the recognized word is synthesized and echoed back to the headphone 1 for confirmation (S36). The code corresponding to the recognized word is output to the system side (S37).

The commands and pathological finding data used in this pathological examination support system will be described.

FIG. 4 shows an input screen displayed on the display device 7 for inputting a finding while looking at the microscope. 40 is a title describing the object of this data input. Reference numeral 41 is a column for displaying data registered in the system. 42 is a field for inputting data to be registered. 43-46 have shown each data item (field) which should be input. In this system, "finding" 43, "Grd (grade)"
44, “site” 45, “qualifier”
) ”46 and the like. Reference numeral 47 denotes an icon, and by pointing this with the mouse, the command described therein is executed. In addition, even if the key on the keyboard described there is pressed, the command is executed. Reference numeral 48 is a cursor displayed below the line, which indicates the line in which data is being input. Further, the input target items are distinguished by reverse display or blinking display of the cursor.

A case where data is input by voice to each item on the display screen will be described. Input observations while observing the dog's liver with a microscope. First, type in the finding item of the current line where the cursor is. In voice
generation, fatty "is recognized and this word is displayed in the item of this finding. As for the recognized word, the speech-synthesized word is responded to the headphone, so that it is possible to confirm what was recognized as the speech. As in this case, two words can be input in one item. Next, the degree (Grd) of the finding is input as a number. For example, if you say "severe",
“Re” is converted to “3” and displayed in the corresponding item.

If you make a mistake, enter the command "clea
Entering "r" erases the word entered in that item. In addition, when moving an item to be input, when the user moves to the item to be moved (speaks the item to be input), this becomes a command and moves to that item. For example, "gr
ade], the input target moves to the item "Grd".

When inputting the next finding, when the command "finding add" is uttered, the process moves to the input of the next line.

When the input is completed and a plurality of input lines are to be registered (moved to the column 41 in FIG. 4),
Say "entry". Then, the line that has been in the input field 42 until now is moved to the registration field 41.

Here, it may happen that the user observes the microscope for a long time and cannot know which item is the input target. In this case, when uttering "where field", for example, "grade" is returned to the headphones, and the item to be input is known. The processing of this "where field" command is shown in FIG.

When uttering "where field", the voice recognition and synthesis circuit 3 recognizes the voice and sends the word to the pathological examination support system. Since the sent word is a command in the pathological examination support system, the command is processed. FIG. 5 shows the processing from here. "Where
In the processing of "field", the position of the input target item is read from the position where the position of the input target item is stored in the system (S
51). This position is changed to the item name (for example, "grade") (S52) and sent to the voice recognition / synthesis device 3 (S5).
3). The voice recognition synthesizing device 3 synthesizes the item name by voice and brings it to the headphones 1. The operator hears "grade" in the voice, and thus can know the input target item.

Although the above embodiment has been described with respect to the pathological examination support system, the present invention can be applied to all systems in which itemized data is input by voice.

[0025]

According to the present invention, by using the voice recognition / synthesis apparatus, data input can be performed entirely by voice without looking at the screen. Therefore, while performing work, it is possible to input data related to the work without interrupting the work.

[Brief description of drawings]

FIG. 1 is a diagram showing a system configuration of the present invention.

FIG. 2 is a flowchart illustrating a voice recognition operation.

FIG. 3 is a flowchart for explaining a data input operation of the present invention.

FIG. 4 is a diagram showing a display screen of the present invention.

FIG. 5 shows a command “where field” of the commands of the present invention.
7 is a flowchart for explaining the operation of "d".

[Explanation of symbols]

 1 Headphones (earphones etc.) 2 Microphone 3 Voice recognition / synthesis device 4 CPU 5 Memory 6 Display device interface 7 Display device 8 Keyboard / mouse interface 9 Keyboard 10 Mouse 11 External storage device such as disk device

─────────────────────────────────────────────────── ─── Continuation of the front page (51) Int.Cl. ⁶ Identification code Internal reference number FI Technical display location G10L 3/00 551 L 561 D // G01N 35/00 A

Claims (6)

[Claims] 1. A voice data input device for inputting itemized data by voice, a voice input means for inputting voice and a voice output means for outputting voice, a display means for displaying the input item data, and a voice input. Means for recognizing voiced itemized data and commands, means for voice-outputting the voiced itemized data and commands by voice synthesis, and means for inputting / displaying the voice-inputted item data on the item And a means for performing processing according to the voice input command, the voice data input device. 2. The voice data input device according to claim 1, wherein the command includes an item movement command. 3. The voice data input device according to claim 2, wherein the item movement command specifies an item name. 4. The command according to claim 1, wherein the command includes a command for confirming an input target item.
The voice data input device according to claim 1. 5. The voice data input device according to claim 4, wherein the command for confirming the input target item responds by voice to the input target item. 6. The voice data input device according to claim 1, which is applied to a pathological examination support system.